© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 11678
    Prev
    Next
    INDEX
    Explanations

    Cardinal and ordinal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çħ
    -0.11
    ening
    -0.10
    æ¼ī
    -0.09
    ally
    -0.09
    entic
    -0.09
    è·
    -0.09
    èİł
    -0.09
    íį¼
    -0.08
    人æ°ijæľįåĬ¡
    -0.08
    лив
    -0.08
    POSITIVE LOGITS
     обÑĢазом
    0.11
    ä¸Ńå¼ı
    0.10
    ANCE
    0.10
    ize
    0.10
    ization
    0.09
    -addon
    0.09
    们
    0.09
    ities
    0.09
    ató
    0.09
    们çļĦ
    0.09
    Activations Density 0.003%

    No Known Activations